Can I read SyntaxNet Models for the CoNLL 2017 Shared Task on EtoBox?

SyntaxNet Models for the CoNLL 2017 Shared Task by Alberti, Chris; Andor, Daniel; Bogatyy, Ivan; Collins, Michael; Gillick, Dan; Kong, Lingpeng; Koo, Terry; Ma, Ji; Omernick, Mark; Petrov, Slav; Thanapirom, Chayut; Tung, Zora; Weiss, David is a scholarly article available to read on EtoBox.

What is SyntaxNet Models for the CoNLL 2017 Shared Task about?

We describe a baseline dependency parsing system for the CoNLL2017 Shared Task. This system, which we call "ParseySaurus," uses the DRAGNN framework [Kong et al, 2017] to combine transition-based recurrent parsing and tagging with character-based word representations. On the v1.3 Universal Dependencies Treebanks, the new system outpeforms the publicly available, state-of-the-art "Parsey's Cousins" models by 3.47% absolute Labeled Accuracy Score (LAS) across 52 treebanks.

Author

Alberti, Chris; Andor, Daniel; Bogatyy, Ivan; Collins, Michael; Gillick, Dan; Kong, Lingpeng; Koo, Terry; Ma, Ji; Omernick, Mark; Petrov, Slav; Thanapirom, Chayut; Tung, Zora; Weiss, David

Published

2017

Language

EN